Crawler Summary

openclaw-auditor answer-first brief

Audit OpenClaw agent proposals and troubleshoot OpenClaw configuration issues. Trigger when: (1) user shares a Notion page containing an OpenClaw agent's proposal for review/audit, (2) user asks about OpenClaw configuration, troubleshooting, or architecture, (3) user mentions OpenClaw, Galatea (agent name), openclaw.json, or Gateway issues, (4) user asks to review or fix broken channel integrations (Discord, Feishu, Telegram, WhatsApp, etc.), (5) user references config.apply, config.patch, openclaw doctor, or any OpenClaw CLI command. This skill is for Claude (claude.ai) acting as an external auditor for OpenClaw agent outputs, using Notion as the communication bridge between Claude and the OpenClaw agent. --- name: openclaw-auditor description: > Audit OpenClaw agent proposals and troubleshoot OpenClaw configuration issues. Trigger when: (1) user shares a Notion page containing an OpenClaw agent's proposal for review/audit, (2) user asks about OpenClaw configuration, troubleshooting, or architecture, (3) user mentions OpenClaw, Galatea (agent name), openclaw.json, or Gateway issues, (4) user asks to review or fix brok Capability contract not published. No trust telemetry is available yet. Last updated 2/24/2026.

Freshness

Last checked 2/24/2026

Best For

openclaw-auditor is best for content workflows where MCP and OpenClaw compatibility matters.

Not Ideal For

Contract metadata is missing or unavailable for deterministic execution.

Evidence Sources Checked

editorial-content, GITHUB OPENCLEW, runtime-metrics, public facts pack

Claim this agent
Agent DossierGitHubSafety: 89/100

openclaw-auditor

Audit OpenClaw agent proposals and troubleshoot OpenClaw configuration issues. Trigger when: (1) user shares a Notion page containing an OpenClaw agent's proposal for review/audit, (2) user asks about OpenClaw configuration, troubleshooting, or architecture, (3) user mentions OpenClaw, Galatea (agent name), openclaw.json, or Gateway issues, (4) user asks to review or fix broken channel integrations (Discord, Feishu, Telegram, WhatsApp, etc.), (5) user references config.apply, config.patch, openclaw doctor, or any OpenClaw CLI command. This skill is for Claude (claude.ai) acting as an external auditor for OpenClaw agent outputs, using Notion as the communication bridge between Claude and the OpenClaw agent. --- name: openclaw-auditor description: > Audit OpenClaw agent proposals and troubleshoot OpenClaw configuration issues. Trigger when: (1) user shares a Notion page containing an OpenClaw agent's proposal for review/audit, (2) user asks about OpenClaw configuration, troubleshooting, or architecture, (3) user mentions OpenClaw, Galatea (agent name), openclaw.json, or Gateway issues, (4) user asks to review or fix brok

MCPself-declared
OpenClawself-declared

Public facts

4

Change events

1

Artifacts

0

Freshness

Feb 24, 2026

Verifiededitorial-contentNo verified compatibility signals

Capability contract not published. No trust telemetry is available yet. Last updated 2/24/2026.

Trust evidence available

Trust score

Unknown

Compatibility

MCP, OpenClaw

Freshness

Feb 24, 2026

Vendor

Charpup

Artifacts

0

Benchmarks

0

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Capability contract not published. No trust telemetry is available yet. Last updated 2/24/2026.

Setup snapshot

git clone https://github.com/Charpup/openclaw-auditor.git
  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Charpup

profilemedium
Observed Feb 24, 2026Source linkProvenance
Compatibility (1)

Protocol compatibility

MCP, OpenClaw

contractmedium
Observed Feb 24, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB OPENCLEW

Extracted files

0

Examples

2

Snippets

0

Languages

typescript

Parameters

Executable Examples

bash

curl -s -H "Accept: text/markdown" "https://docs.openclaw.ai/<path>"

bash

curl -s -H "Accept: text/markdown" "https://docs.openclaw.ai/<path>"

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Audit OpenClaw agent proposals and troubleshoot OpenClaw configuration issues. Trigger when: (1) user shares a Notion page containing an OpenClaw agent's proposal for review/audit, (2) user asks about OpenClaw configuration, troubleshooting, or architecture, (3) user mentions OpenClaw, Galatea (agent name), openclaw.json, or Gateway issues, (4) user asks to review or fix broken channel integrations (Discord, Feishu, Telegram, WhatsApp, etc.), (5) user references config.apply, config.patch, openclaw doctor, or any OpenClaw CLI command. This skill is for Claude (claude.ai) acting as an external auditor for OpenClaw agent outputs, using Notion as the communication bridge between Claude and the OpenClaw agent. --- name: openclaw-auditor description: > Audit OpenClaw agent proposals and troubleshoot OpenClaw configuration issues. Trigger when: (1) user shares a Notion page containing an OpenClaw agent's proposal for review/audit, (2) user asks about OpenClaw configuration, troubleshooting, or architecture, (3) user mentions OpenClaw, Galatea (agent name), openclaw.json, or Gateway issues, (4) user asks to review or fix brok

Full README

name: openclaw-auditor description: > Audit OpenClaw agent proposals and troubleshoot OpenClaw configuration issues. Trigger when: (1) user shares a Notion page containing an OpenClaw agent's proposal for review/audit, (2) user asks about OpenClaw configuration, troubleshooting, or architecture, (3) user mentions OpenClaw, Galatea (agent name), openclaw.json, or Gateway issues, (4) user asks to review or fix broken channel integrations (Discord, Feishu, Telegram, WhatsApp, etc.), (5) user references config.apply, config.patch, openclaw doctor, or any OpenClaw CLI command. This skill is for Claude (claude.ai) acting as an external auditor for OpenClaw agent outputs, using Notion as the communication bridge between Claude and the OpenClaw agent.

OpenClaw Auditor

Purpose

Act as a safety net and quality auditor for OpenClaw agent (Galatea) operations. The agent has high operational privileges but limited schema awareness, frequently breaking its own configuration. Claude reviews agent proposals, catches errors before execution, and provides better alternatives.

Research Workflow

When encountering an OpenClaw problem, follow this priority order:

1. Check local references first

  • Read references/schema-quick-ref.md for config node overview and common pitfalls
  • Read references/resources.md for the full resource index

2. Fetch official documentation

  • Primary: https://docs.openclaw.ai/gateway/configuration
  • Config examples: https://docs.openclaw.ai/gateway/configuration-examples
  • Troubleshooting: https://docs.openclaw.ai/gateway/troubleshooting
  • Doctor: https://docs.openclaw.ai/gateway/doctor
  • Always fetch with Accept: text/markdown header — the docs site supports content negotiation and returns clean Markdown (no HTML noise) when this header is present. Use Bash + curl instead of web_fetch for these URLs:
    curl -s -H "Accept: text/markdown" "https://docs.openclaw.ai/<path>"
    
    This avoids HTML-to-Markdown conversion artefacts and gives directly usable content.

3. Search GitHub Issues and Discussions

  • Issues: https://github.com/openclaw/openclaw/issues — search for error messages or symptoms
  • Discussions: https://github.com/openclaw/openclaw/discussions — search for community solutions
  • Use web_search with queries like: site:github.com/openclaw/openclaw/issues <error_keyword>

4. Check ClawHub for existing skills

  • Registry: https://clawhub.ai/skills
  • Awesome list: https://github.com/VoltAgent/awesome-openclaw-skills
  • Search before building custom solutions to avoid reinventing the wheel

5. Check the config-validator skill

  • Schema reference: https://github.com/Charpup/openclaw-config-validator
  • Contains complete schema docs for OpenClaw 2026.2.1+ (22 top-level nodes)
  • Includes validation scripts and forbidden fields list

Audit Process

When reviewing an agent proposal from a Notion page:

  1. Read the Notion page — understand what the agent proposes to do and why
  2. Identify risk level — categorize the proposed changes:
    • 🟢 Low risk: workspace files, SOUL.md, AGENTS.md, skill installation
    • 🟡 Medium risk: channel config, model settings, tool policies
    • 🔴 High risk: gateway settings, auth config, config.apply (full replace), sandbox settings
  3. Validate against schema — check proposed config changes against known schema structure
  4. Research if needed — follow the research workflow above for unfamiliar areas
  5. Write audit result back to Notion — include:
    • Risk assessment
    • Issues found (if any)
    • Recommended approach (if different from proposal)
    • Relevant documentation links
    • Specific commands or config snippets ready for execution

Key Safety Rules

  • config.apply replaces the ENTIRE config. Prefer config.patch for partial updates.
  • Always recommend cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.bak before changes.
  • openclaw doctor is the first diagnostic step for any startup failure.
  • Gateway refuses to start on invalid config — only diagnostic commands work in this state.
  • Never add fields that don't exist in the schema (common agent mistake).
  • Channel account keys vary: WhatsApp uses credential dirs, Telegram/Discord use botToken.

Notion Interaction Protocol

  • Notion is the bridge between Claude and the OpenClaw agent
  • User provides Notion page links; read via Notion MCP tools
  • Write audit results and instructions back to the same or linked Notion pages
  • If context on a Notion page is insufficient, ask the user to request more detail from the agent
  • Keep instructions to the agent action-oriented and executable

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

MissingGITHUB OPENCLEW

Contract coverage

Status

missing

Auth

None

Streaming

No

Data region

Unspecified

Protocol support

MCP: self-declaredOpenClaw: self-declared

Requires: none

Forbidden: none

Guardrails

Operational confidence: low

No positive guardrails captured.
Invocation examples
curl -s "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/snapshot"
curl -s "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/contract"
curl -s "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

Do not use if

Contract metadata is missing or unavailable for deterministic execution.
No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
GITLAB_AI_CATALOGgitlab-mcp

Rank

83

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP
GITLAB_PUBLIC_PROJECTSgitlab-mcp

Rank

80

A Model Context Protocol (MCP) server for GitLab

Traction

No public download signal

Freshness

Updated 2d ago

MCP
GITLAB_AI_CATALOGrmcp-openapi

Rank

74

Expose OpenAPI definition endpoints as MCP tools using the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP
GITLAB_AI_CATALOGrmcp-actix-web

Rank

72

An actix_web backend for the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)

Traction

No public download signal

Freshness

Updated 2d ago

MCP
Machine Appendix

Contract JSON

{
  "contractStatus": "missing",
  "authModes": [],
  "requires": [],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": null,
  "outputSchemaRef": null,
  "dataRegion": null,
  "contractUpdatedAt": null,
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/snapshot",
    "contractUrl": "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/contract",
    "trustUrl": "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/trust"
  },
  "curlExamples": [
    "curl -s \"https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/snapshot\"",
    "curl -s \"https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/contract\"",
    "curl -s \"https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "MCP",
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-04-16T23:34:35.848Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "MCP",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "content",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:MCP|unknown|profile protocol:OPENCLEW|unknown|profile capability:content|supported|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Charpup",
    "href": "https://github.com/Charpup/openclaw-auditor",
    "sourceUrl": "https://github.com/Charpup/openclaw-auditor",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:44:34.168Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "MCP, OpenClaw",
    "href": "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/contract",
    "sourceUrl": "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:44:34.168Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/trust",
    "sourceUrl": "https://xpersona.co/api/v1/agents/charpup-openclaw-auditor/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub · GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to openclaw-auditor and adjacent AI workflows.